• 전기학회논문지
• /
• 제58권1호
• /
• pp.1-6
• /
• 2009

The traditional demand prediction was based on the technique wherein electric power corporations made monthly or seasonal estimation of electric power consumption for each area and subscription type for the next one or two years to consider both seasonally generated and local consumed amounts. Note, however, that techniques such as pricing, power generation plan, or sales strategy establishment were used by corporations without considering the production, comparison, and analysis techniques of the predicted consumption to enable efficient power consumption on the actual demand side. In this paper, to calculate the predicted value of electric power consumption on a short-term basis (15 minutes) according to the amount of electric power actually consumed for 15 minutes on the demand side, we performed comparison and analysis by applying a 15-minute interval prediction technique to the average and that to the time series analysis to show how they were made and what we obtained from the simulations.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.594-597
• /
• 2007

We present in this paper a novel mid and long term power load prediction method using temporal pattern mining from AMR (Automatic Meter Reading) data. Since the power load patterns have time-varying characteristic and very different patterns according to the hour, time, day and week and so on, it gives rise to the uninformative results if only traditional data mining is used. Also, research on data mining for analyzing electric load patterns focused on cluster analysis and classification methods. However despite the usefulness of rules that include temporal dimension and the fact that the AMR data has temporal attribute, the above methods were limited in static pattern extraction and did not consider temporal attributes. Therefore, we propose a new classification method for predicting power load patterns. The main tasks include clustering method and temporal classification method. Cluster analysis is used to create load pattern classes and the representative load profiles for each class. Next, the classification method uses representative load profiles to build a classifier able to assign different load patterns to the existing classes. The proposed classification method is the Calendar-based temporal mining and it discovers electric load patterns in multiple time granularities. Lastly, we show that the proposed method used AMR data and discovered more interest patterns.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권10호
• /
• pp.1-13
• /
• 2022

This paper empirically explores the predicting ability of the newly proposed smooth transition (ST) time-varying combining forecast methods. The proposed method allows the "weight" of combining forecasts to change gradually over time through its unique feature of transition variables. Stock market returns from 7 countries were applied to Ad Hoc models, the well-known Generalized Autoregressive Conditional Heteroskedasticity (GARCH) family models, and the Smooth Transition Exponential Smoothing (STES) models. Of the individual models, GJRGARCH and STES-E&AE emerged as the best models and thereby were chosen for constructing the combined forecast models where a total of nine ST combining methods were developed. The robustness of the ST combining forecasts is also validated by the Diebold-Mariano (DM) test. The post-sample forecasting performance shows that ST combining forecast methods outperformed all the individual models and fixed weight combining models. This study contributes in two ways: 1) the ST combining methods statistically outperformed all the individual forecast methods and the existing traditional combining methods using simple averaging and Bates & Granger method. 2) trading volume as a transition variable in ST methods was superior to other individual models as well as the ST models with single sign or size of past shocks as transition variables.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.177-182
• /
• 2022

Technology is progressing with every passing day and the enormous usage of electricity is becoming a necessity. One of the techniques to enjoy the assistances in a smart home is the efficiency to manage the electric energy. When electric energy is managed in an appropriate way, it drastically saves sufficient power even to be spent during hard time as when hit by natural calamities. To accomplish this, prediction of energy consumption plays a very important role. This proposed prediction model Coherent Weighted K-Means Clustering ARIMA (CWKMCA) enhances the weighted k-means clustering technique by adding weights to the cluster points. Forecasting is done using the ARIMA model based on the centroid of the clusters produced. The dataset for this proposed work is taken from the Pecan Project in Texas, USA. The level of accuracy of this model is compared with the traditional ARIMA model and the Weighted K-Means Clustering ARIMA Model. When predicting,errors such as RMSE, MAPE, AIC and AICC are analysed, the results of this suggested work reveal lower values than the ARIMA and Weighted K-Means Clustering ARIMA models. This model also has a greater loglikelihood, demonstrating that this model outperforms the ARIMA model for time series forecasting.

• 무역학회지
• /
• 제46권6호
• /
• pp.191-209
• /
• 2021

In this paper, various time series analysis models and machine learning models are presented for long-term prediction of export growth rate, and the prediction performance is compared and reviewed by RMSE and MAE. Export growth rate is one of the major economic indicators to evaluate the economic status. And It is also used to predict economic forecast. The export growth rate may have a negative (-) value as well as a positive (+) value. Therefore, Instead of using the ReLU function, which is often used for time series prediction of deep learning models, the PReLU function, which can have a negative (-) value as an output value, was used as the activation function of deep learning models. The time series prediction performance of each model for three types of data was compared and reviewed. The forecast data of long-term prediction of export growth rate was deduced by three forecast methods such as a fixed forecast method, a recursive forecast method and a rolling forecast method. As a result of the forecast, the traditional time series analysis model, ARDL, showed excellent performance, but as the time period of learning data increases, the performance of machine learning models including LSTM was relatively improved.

• 한국임상보건과학회지
• /
• 제2권2호
• /
• pp.126-132
• /
• 2014

Purpose. Because traditional statistics approach had limitations in learning future forecasting and major factors causing occupational injuries in each industry, this paper develops a model forecasting and evaluating occupational injury rate by using a system dynamics model through the analysis of the industry injury statistics and the project for industry injury prevention. Method. The model of this paper consists of 12 total models such as a model of employees, of industrial disaster victims, of injury rate, etc.; In the analysis of firm size, it is classified and developed according to 12 groups on the basis of the number of employees, and in the analysis of industrial classification, it is done according to 10 total business fields such as manufacturing business, construction one, etc. Results. This paper suggests the methodology which forecasts industry injury rate by business field and size on the basis of developed model, and evaluates an industry injury prevention project from various angles. Conclusions. This paper deduced problem through the analysis of an industry injury by business fields and a comparative analysis of foreign cases, and analyzed to affect industry injury prevention by industry. And it also analyzed actual condition of industry injury, and did a difference in the level of safety consciousness according to the general characteristics of workers and occupational safety and health education related characteristics. In result, this paper suggests that analyzing occupational injury related factors, a safety budgetary allocation, and industry injury related factors can reduce illness costs such as employees' injury and medical care, and also assist cost for a disability.

• 한국수산과학회지
• /
• 제26권4호
• /
• pp.363-368
• /
• 1993

어획량의 단기 예측은 자원관리에 있어 중요한 항목이지만 전통적인 개체군 모델은 수산자원 관리에 있어 실제적으로 요구되는 예측력이 크게 부족하다. 다종 또는 생태계 모델도 요구되는 매개변수의 수가 많아 실제적 적용이 어렵다. 반면에 단변수 시계열 분석법은 시계열 자체에서 변동성에 관한 특성을 추정하여 이를 토대로 장래 변동성을 예측함으로 최소한의 자료를 가지고 비교적 정확한 단기예측이 가능하므로 유용성이 높다. 본 연구에서는 ARIMA 시계열 모델을 $1971{\sim}1988$년 간의 한국근해의 월별 갈치어획량 자료에 적용하였다. 여기서 나온 예측치와 분석에 포함되지 않았던 $1989{\sim}1990$년 간의 어획량과 비교하였다. 분석 결과 예측치와 실제어획량이 잘 일치하였으며(r=0.938) 평균상대오차는 $59.5\%$였다.

• 디지털콘텐츠학회 논문지
• /
• 제16권3호
• /
• pp.417-424
• /
• 2015

산업의 고도화 및 새로운 기계의 도입, 화학물질 사용 등 산업재해의 다양한 양상과 더불어 생산설비들의 자동화, 대형화로 인해 산업재해 발생의 양상이 점차 다양해지고 있다.국내 산업재해는 OECD(Organization for Economic Cooperation and Development) 경제협력개벌기구대비, 상대적 하위수준에 있어 기업 발생 산업재해는 근로자들의 심리적 및 치료와 보상 손실에도 타격이 되어 기업 총 생산과 이윤 추구에도 중요문제가 야기되고 있다. 더불어, 장애자와 사망유족들의 증가로 생활 안정문제 등 사회적 문제도 제기된다. 이러한 동기에서 본 논문은 산업재해 통계와 산재예방사업을 분석하고, 시스템다이내믹스 법론을 이용하여 산업재해율을 예측하고 평가하는 모델을 개발하였다. 모델은 근로자수 모델, 재해자수 모델, 재해율 모델 등 총 12개의 모델로 구성되었고, 규모별 분석에서는 근로자수를 기준으로 12개 그룹으로, 업종별 분석에서는 제조업, 건설업 등 총 10개의 업종으로 구분하여 개발하였다. 개발된 모델을 토대로 업종별 규모별 산업재해율을 예측하고 산재예방사업을 다각도로 평가하는 방법론을 제시하였다.

• 한국가스학회지
• /
• 제23권5호
• /
• pp.52-58
• /
• 2019

본 연구에서는 국내 도시가스 인수량에 대한 예측 모델을 개발하였다. 국내의 도시가스 회사는 KOGAS에 차년도 수요를 예측하여 보고해야 하므로 도시가스 인수량 예측은 도시가스 회사에 중요한 사안이다. 도시가스 사용량에 영향을 미치는 요인은 용도구분에 따라 다소 상이하나, 인수량 데이터는 용도별 구분이 어렵기 때문에 특정 용도에 관계없이 영향을 주는 요인으로 외기온도를 고려하여 모델개발을 실시하였다.실험 및 검증은 JB주식회사의 2008년부터 2018년까지 총 11년 치 도시가스 인수량 데이터를 사용하였으며, 전통적인 시계열 분석 중 하나인 ARIMA(Auto-Regressive Integrated Moving Average)와 딥러닝 기법인 LSTM(Long Short-Term Memory)을 이용하여 각각 예측 모델을 구축하고 두 방법의 단점을 최소화하기 위하여 다양한 앙상블(Ensemble) 기법을 사용하였다. 본 연구에서 제안한 일별 예측의 오차율 절댓값 평균은 Ensemble LSTM 기준 0.48%, 월별 예측의 오차율 절댓값 평균은 2.46%, 1년 예측의 오차율 절댓값 평균은 5.24%임을 확인하였다.

• 한국ITS학회 논문지
• /
• 제20권3호
• /
• pp.59-73
• /
• 2021

교통사고로 인한 많은 인명피해가 발생하고 있으나, 첨단 기술의 발전에도 불구하고 교통사고 발생은 줄어들지 않고 있다. 교통사고를 사전에 예방하기 위해서는 향후 사고가 어떻게 변화하여 갈 것인지를 정확하게 예측할 필요가 있다. 지금까지 교통사고 발생 빈도 예측은 주요 연구 분야가 아니었으며 주로 과거 일정 기간의 통계를 기반으로 전통적인 방법으로 미시적으로 분석되어 왔다. 최근 AI 기술이 교통사고 분야에 도입 되었음에도 불구하고 주로 교통 흐름 예측에 초점을 맞추고 있어, 본 연구에서는 2014년부터 2019년까지 국내에서 발생한 1,339,587건의 교통사고 기록을 시계열 데이터로 변환하고 AI 알고리즘 LSTM을 이용하여 연령별, 시간별 교통사고 발생 빈도를 예측하였다. 또한 코로나-19로 인한 교통 환경의 변화에 맞추어 예측값과 실제값을 비교 검증하였다. 향후 이러한 연구결과가 교통사고 예방의 정책개선으로 이어지고 사고 예방에 활용 될 것으로 기대된다.